refactor CPU llama inference code #728
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update. |
yao-matrix
reviewed
May 27, 2024
jiqing-feng
reviewed
May 30, 2024
echarlaix
reviewed
Jun 6, 2024
Comment on lines
-234
to
-238
| if is_transformers_version("<", _TRANSFORMERS_MIN_VERSION) or is_transformers_version( | ||
| ">", _TRANSFORMERS_MAX_VERSION | ||
| ): | ||
| raise ImportError( | ||
| f"Only transformers versions {_TRANSFORMERS_MIN_VERSION} ~ {_TRANSFORMERS_MAX_VERSION} are verified." |
There was a problem hiding this comment.
We should keep this as only the transformers versions in between are supported, but this should be moved what do you think about :
There was a problem hiding this comment.
yes, totally agree! code updated.
There was a problem hiding this comment.
thanks for the detailed review! the rebase and merge conflict did bring some headache
Co-authored-by: Ella Charlaix <80481427+echarlaix@users.noreply.github.com>
|
Hi @echarlaix , I manually-checked the changes in #725 and fixed the bugs introduced through rebasing. Now all tests passed, I think we are good to go. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
What does this PR do?
This PR refactors the current CPU llama inference code to make code clean. The major changes are as follows:
_IPEXLlamaAttentionand move the attention-related OPs and attention forward code to_IPEXLlamaAttention_IPEXLlamaMLPand move the MLP-related OPs and forward code to_IPEXLlamaMLP_patch_llama_model_IPEXLlamaDecoderLayerRefto_IPEXLlamaDecoderLayer_IPEXLlamaAttentionintogemm,ropeandsdpaPlease note that this PR is based on the unmerged PR #725 by Jiqing as can be seen in the commit history.